Название: Learning Tensorflow.js (Early Release)
Автор: Gant Laborde
Издательство: O’Reilly Media, Inc
Год: 2021-02-11:
Формат: epub/azw3/pdf(conv.)
Размер: 10.7 Mb
Язык: English

Combining the demand for AI with the ubiquity of jаvascript was inevitable. With Google's TensorFlow.js framework, seasoned AI veterans and web developers alike can help propel the future of AI-driven websites. In this guide, author Gant Laborde--Google Developer Expert in machine learning and the web--provides a hands-on, end-to-end approach to TensorFlow.js fundamentals for a broad technical audience that includes data scientists, engineers, web developers, students, and researchers.
You'll begin by working through some basic examples in TensorFlow.js before diving deeper into neural network architectures, DataFrames, TensorFlow Hub, model conversion, transfer learning, and more. Once you finish this book, you'll know how to build and deploy production-ready deep learning systems with TensorFlow.js.
Explore tensors, the most fundamental structure of machine learning
Convert data into tensors and back with a real-world example
Combine AI with the web using TensorFlow.js and other tools
Use resources to convert, train, and manage machine learning data
Start building and training your own training models from scratch
Learn how to create your own image classification models
Examine transfer learning: retraining an advanced model to perform a new task